deriva-ml 1.14.26__tar.gz → 1.14.27__tar.gz

{deriva_ml-1.14.26/src/deriva_ml.egg-info → deriva_ml-1.14.27}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.26
+Version: 1.14.27
 Summary: Utilities to simplify use of Dervia and Pandas to create reproducable ML pipelines
 Author-email: ISRD <isrd-dev@isi.edu>
 Requires-Python: >=3.10

{deriva_ml-1.14.26 → deriva_ml-1.14.27}/src/deriva_ml/dataset/dataset.py

@@ -211,6 +211,7 @@ class Dataset:
         dataset_path.update([{"RID": dataset, "Version": version["RID"]} for dataset, version in versions.items()])
 
     def _set_version_snapshot(self):
+        """Update the Snapshot column of the Dataset_Version table to the correct time."""
         dataset_version_path = self._model.catalog.getPathBuilder().schemas[self._ml_schema].tables["Dataset_Version"]
         versions = dataset_version_path.entities().fetch()
         dataset_version_path.update(
@@ -1023,7 +1024,7 @@ class Dataset:
                 self._logger.info(
                     "Downloading dataset %s for catalog: %s@%s"
                     % (
-                        'minid' if self._use_minid else 'bag',
+                        "minid" if self._use_minid else "bag",
                         dataset.rid,
                         str(dataset.version),
                     )

{deriva_ml-1.14.26 → deriva_ml-1.14.27}/src/deriva_ml/execution/workflow.py

@@ -305,14 +305,14 @@ class Workflow(BaseModel):
             is_notebook = False
             stack = inspect.stack()
             # Get the caller's filename, which is two up the stack from here.
-            if len(stack) > 1:
-                filename = Path(stack[2].filename)
-                if not filename.exists():
-                    # Being called from the command line interpreter.
-                    filename = Path("REPL")
-                # Get the caller's filename, which is two up the stack from here.
-            else:
-                raise DerivaMLException("Looking for caller failed")  # Stack is too shallow
+
+            filename = Path(stack[-1].filename)
+            if not filename.exists():
+                # Being called from the command line interpreter.
+                filename = Path("REPL")
+            # Get the caller's filename, which is two up the stack from here.
+        else:
+            raise DerivaMLException("Looking for caller failed")  # Stack is too shallow
         return filename, is_notebook
 
     @staticmethod

{deriva_ml-1.14.26 → deriva_ml-1.14.27/src/deriva_ml.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deriva-ml
-Version: 1.14.26
+Version: 1.14.27
 Summary: Utilities to simplify use of Dervia and Pandas to create reproducable ML pipelines
 Author-email: ISRD <isrd-dev@isi.edu>
 Requires-Python: >=3.10

{deriva_ml-1.14.26 → deriva_ml-1.14.27}/src/deriva_ml.egg-info/SOURCES.txt

@@ -94,6 +94,8 @@ tests/dataset/test_datasets.py
 tests/dataset/test_download.py
 tests/execution/__init__.py
 tests/execution/test_execution.py
+tests/execution/workflow-script.py
+tests/execution/workflow_test.ipynb
 tests/feature/test_features.py
 tests/model/__init__.py
 tests/model/test_database.py

{deriva_ml-1.14.26 → deriva_ml-1.14.27}/tests/execution/test_execution.py

@@ -2,6 +2,8 @@
 Tests for the execution module.
 """
 
+import re
+import subprocess
 from tempfile import TemporaryDirectory
 
 from deriva_ml import (
@@ -16,6 +18,59 @@ from deriva_ml import (
 )
 
 
+class TestWorkflow:
+    def test_workflow_creation_script(self, test_ml):
+        ml_instance = test_ml
+        ml_instance.add_term(vc.asset_type, "Test Model", description="Model for our Test workflow")
+        ml_instance.add_term(vc.workflow_type, "Test Workflow", description="A ML Workflow that uses Deriva ML API")
+        print("Running workflow-script.py ...")
+        result = subprocess.run(
+            [
+                "python",
+                "execution/workflow-script.py",
+                ml_instance.catalog.deriva_server.server,
+                ml_instance.catalog_id,
+            ],
+            capture_output=True,
+            text=True,
+        )
+        print(result.stdout)
+        m = re.match(".*url='(?P<url>.*?)'", result.stdout)
+        url = m["url"]
+        m = re.match(".*checksum='(?P<checksum>.*?)'", result.stdout)
+        checksum = m["checksum"]
+        m = re.match(".*is_notebook=(?P<is_notebook>True|False)", result.stdout)
+        is_notebook = m["is_notebook"]
+        print("URL", url)
+        print("checksum", checksum)
+        print("is_notebook", is_notebook)
+        assert is_notebook == "False"
+        assert url.endswith("workflow-script.py")
+
+    def test_workflow_creation_notebook(self, test_ml):
+        ml_instance = test_ml
+        ml_instance.add_term(vc.asset_type, "Test Model", description="Model for our Test workflow")
+        ml_instance.add_term(vc.workflow_type, "Test Workflow", description="A ML Workflow that uses Deriva ML API")
+        print("Running workflow-script.py ...")
+        result = subprocess.run(
+            ["runnotebook", "execution/workflow-script.ipnb", "localhost", ml_instance.catalog_id],
+            capture_output=True,
+            text=True,
+        )
+        print(result.stdout)
+        m = re.match(".*url='(?P<url>.*?)'", result.stdout)
+        url = m["url"]
+        m = re.match(".*checksum='(?P<checksum>.*?)'", result.stdout)
+        checksum = m["checksum"]
+        m = re.match(".*is_notebook=(?P<is_notebook>True|False)", result.stdout)
+        is_notebook = m["is_notebook"]
+        print("URL", url)
+        print("checksum", checksum)
+        print("is_notebook", is_notebook)
+        assert is_notebook == "False"
+        assert url.endswith("workflow-script.py")
+
+
 class TestExecution:
     def test_execution_no_download(self, test_ml):
         ml_instance = test_ml

deriva_ml-1.14.27/tests/execution/workflow-script.py

@@ -0,0 +1,19 @@
+import sys
+
+from deriva_ml import DerivaML
+from deriva_ml import MLVocab as vc
+
+hostname = sys.argv[1]
+catalog_id = sys.argv[2]
+
+
+ml_instance = DerivaML(hostname, catalog_id)
+
+ml_instance.add_term(vc.asset_type, "Test Model", description="Model for our Test workflow")
+ml_instance.add_term(vc.workflow_type, "Test Workflow", description="A ML Workflow that uses Deriva ML API")
+api_workflow = ml_instance.create_workflow(
+    name="Test Workflow One",
+    workflow_type="Test Workflow",
+    description="A test operation",
+)
+print(api_workflow)

deriva_ml-1.14.27/tests/execution/workflow_test.ipynb

@@ -0,0 +1,94 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0",
+   "metadata": {},
+   "source": [
+    "# Notebook template for executing code using DerivaML.\n",
+    "\n",
+    "This notebook should be modified to perform the desired calcuation and *COMITTED* to Gihub prior to execution."
+   ]
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-18T20:05:17.505817Z",
+     "start_time": "2025-04-18T20:05:16.235245Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "from deriva_ml import DerivaML, MLVocab as vc\n",
+    "import os"
+   ],
+   "id": "2c6cbcfe94814682",
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Parameters cell\n",
+   "id": "2af30ff79278ba00"
+  },
+  {
+   "metadata": {
+    "tags": [
+     "parameters"
+    ]
+   },
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "hostname = None\n",
+    "catalog_id = None"
+   ],
+   "id": "3"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "# Modify these to your desired server and catalog.\n",
+    "hostname = hostname or os.environ.get(\"DERIVA_HOST\")\n",
+    "catalog_id = catalog_id or os.environ.get(\"DERIVA_CATALOG_ID\")\n",
+    "\n",
+    "# Change this line to call the domain specific class derived from DerivaML\n",
+    "deriva_ml = DerivaML(hostname=hostname, catalog_id=catalog_id)\n",
+    "deriva_ml.add_term(vc.asset_type, \"Test Model\", description=\"Model for our Test workflow\")\n",
+    "deriva_ml.add_term(vc.workflow_type, \"Test Workflow\", description=\"A ML Workflow that uses Deriva ML API\")\n",
+    "api_workflow = deriva_ml.create_workflow(\n",
+    "    name=\"Test Workflow One\",\n",
+    "    workflow_type=\"Test Workflow\",\n",
+    "    description=\"A test operation\",\n",
+    ")\n"
+   ],
+   "id": "1"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "deriva-test",
+   "language": "python",
+   "name": "deriva-test"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}